Robust bayesian inference of generalized Pareto distribution

Abstract

Abstract. In this work, robust Bayesian estimation of the generalized Pareto distribution is proposed. The methodology is presented in terms of oscillation of posterior risks of the Bayesian estimators. By using a Monte Carlo simulation study, we show that, under a suitable generalized loss function, we can obtain a robust Bayesian estimator of the model.

Resume. Dans ce travail, nous presentons une analyse de robustesse Bayesienne des estima
teurs des parametres d'un modele de Pareto generalise en termes d'oscillation des risques a posteriori. En utilisant une etude exhaustive de Monte Carlo, nous prouvons que, moyennant une fonction perte generalisee adequate, on peut construire un estimateur Bayesien robuste du modele.

Key words: Bayesian estimation; Extreme value; Generalized Fisher information; Gener-
alized Pareto distribution; Monte Carlo; Robustness.